ss

pages/3_Training the Model.py

@@ -30,29 +30,16 @@ def process_file(csv_file):
     return data
 
 
-def model_train(train_X, train_y, model_choice, train_size, tune_model):
+def model_train(train_X, train_y, model_choice, train_size):
     if model_choice == 'LightGBM':
-        model = lgb.LGBMRegressor() if not tune_model else lgb.LGBMRegressor(**tuned_parameters('lgbm'))
+        model = lgb.LGBMRegressor()
     elif model_choice == 'Random Forest':
-        model = RandomForestRegressor(n_estimators=100, random_state=42) if not tune_model else RandomForestRegressor(**tuned_parameters('rf'))
+        model = RandomForestRegressor(n_estimators=100, random_state=42)
 
     X_train, X_test, y_train, y_test = train_test_split(train_X, train_y, train_size=train_size/100, random_state=42, shuffle=False)
     model.fit(X_train, y_train)
     return model, X_test, y_test
 
-def model_predict(model, X_test, y_test):
-    if model_choice == 'LightGBM':
-        model = lgb.LGBMRegressor() if not tune_model else lgb.LGBMRegressor(**tuned_parameters('lgbm'))
-    elif model_choice == 'Random Forest':
-        model = RandomForestRegressor(n_estimators=100, random_state=42) if not tune_model else RandomForestRegressor(**tuned_parameters('rf'))
-
-    X_train, X_test, y_train, y_test = train_test_split(train_X, train_y, train_size=train_size/100, random_state=42, shuffle=False)
-
-    model.fit(X_train, y_train)
-    y_pred = model.predict(X_test)
-
-    return y_test, y_pred, model
-
 
 def create_model_inputs(data, lag, mean_period):
     df_processed = data.copy()
@@ -174,16 +161,12 @@ def step3_page():
         with cols[1]:
             st.info("Let's display our Target variable")
             st.dataframe(y)
-    else:
-        pass
 
     if state == "splitting":
         st.subheader("Step 3: Data Splitting")
         st.write("Now let's split the dataset into training and testing sets. The training set is used to train the machine learning model, and the testing set is used to evaluate its performance. For that, you have to select the train-test split %.")
         train_size = st.slider("Select Train Dataset Size (%)", min_value=10, max_value=90, value=70)
         state = "model selection"
-    else:
-        pass
 
     if state == "model selection":
         st.subheader("Step 4: Model Selection")
@@ -191,52 +174,36 @@ def step3_page():
         models = ['LightGBM', 'Random Forest']
         model_choice = st.selectbox('Choose Model', models)
         state = "model training"
-    else:
-        pass
 
     if state == "model training":
         st.subheader("Step 5: Model Training")
-        st.write("Finally, let;s train our weather forecasting model based on the parameters that you have selected!")
-        tune_model = st.checkbox('Tune Hyperparameters')
-
+        st.write("Finally, let's train our weather forecasting model based on the parameters that you have selected!")
         if st.button("Train", key="train"):
-            model, X_test, y_test = model_train(X, y, model_choice, train_size, tune_model)
+            model, X_test, y_test = model_train(X, y, model_choice, train_size)
             my_bar = st.progress(0, text="Training model...")
             for i in range(100):
                 my_bar.progress(i, text="Training model...")
             my_bar.progress(100, text="Training completed")
             state = "model predict"
-    else:
-        pass
-
-    # st.subheader("Step 3: Data Splitting")
-    # st.write(
-    #     "Now let's split into training and testing sets. The training set is used to train the machine learning model, and the testing set is used to evaluate its performance.")
-    # if st.button("Create Features and Target variable"):
-        # train_size = st.sidebar.slider("Select Train Dataset Size (%)", min_value=10, max_value=90, value=70)
-        #
-        # models = ['LightGBM', 'Random Forest']
-        # model_choice = st.sidebar.selectbox('Choose Model', models)
-        #
-        # tune_model = st.sidebar.checkbox('Tune Hyperparameters')
-        #
-        # y_test, y_pred, model = model_predict(data, model_choice, train_size, tune_model)
-        #
-        # # Display feature importance
-        # if st.sidebar.checkbox('Show feature importance'):
-        #     feature_names = ['Solar_Irradiance', 'Temperature', 'Rain_Fall', 'Wind_speed', 'PV_Output_lag',
-        #                      'PV_Output_mean']
-        #     fig = feature_importance_plot(model, feature_names)
-        #     with _lock:
-        #         st.pyplot(fig)
-        #
-        # fig = show_output(y_test, y_pred)
-        #
+            st.success("Model training successfully completed!")
+
+            # Display feature importance
+            if st.checkbox('Show feature importance'):
+                feature_names = ['Solar_Irradiance', 'Temperature', 'Rain_Fall', 'Wind_speed', 'PV_Output_lag',
+                                 'PV_Output_mean']
+                fig = feature_importance_plot(model, feature_names)
+                with _lock:
+                    st.pyplot(fig)
+
+    if state == "model predict":
+        st.subheader("Step 5: Model Evaluation")
+        st.write("Now, let's evaluate our weather forecasting model's performance against the test data set.")
+        y_pred = model.predict(X_test)
+        fig = show_output(y_test, y_pred)
         # download_link(y_test, y_pred)
         #
         # download_plot(fig)
 
-
     if st.button("Complete"):
         complete_level(LEVEL)